Terminal Apparatus for Secure Cloud Character Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing character recognition systems that transmit document images with secret information to cloud servers for processing lack security measures, increasing the risk of information leakage, and are costly due to the need for high-computing performance devices.
Innovation Solution
A terminal apparatus that separates document images into general and secret information components, transmitting only the general information for processing while maintaining the secret information locally, and integrating recognition results to ensure accurate and secure character recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If document images containing secret information are transmitted to cloud servers for character recognition processing, then character recognition accuracy is improved, but the risk of secret information leaking increases
Solution Approach 1:
The patent divides the document image into two separate parts: a general information image (without secret information) and a secret information image (containing only secret information). The general information image is transmitted to the cloud server for character recognition processing, while the secret information image is kept locally and not transmitted. This segmentation resolves the contradiction by enabling accurate character recognition on the transmitted general information while preventing secret information leakage through local retention of the secret portion.
2Measurement precision
If high-computing performance computers with GPU are introduced for character recognition processing, then character recognition accuracy is improved, but system cost increases
Solution Approach 1:
The patent extracts and removes the secret information portion from the document image before transmission to the cloud server. By taking out the secret information image and keeping it locally, the system can utilize cost-effective cloud computing resources for processing the general information image while avoiding the need for expensive high-computing performance computers with GPU at the client side, thus resolving the cost-accuracy contradiction.
3Loss of information
If complete document images are transmitted to cloud servers, then character recognition completeness is improved, but data security deteriorates
Solution Approach 1:
The patent segments the complete document image into general information and secret information portions. The general information image is transmitted to the cloud server for comprehensive character recognition processing, ensuring recognition completeness for non-sensitive content. Meanwhile, the secret information image is retained locally and not transmitted, ensuring data security for sensitive content. This segmentation approach resolves the contradiction between recognition completeness and data security.
Data Source
AI summary
A personal information separation unit separates a document image containing personal information into a personal information image containing the personal information and a general information image that does not contain the personal information on the basis of the document image, and transmits the general information image to a cloud server. A recognition result integration unit receives a general recognition result that is the recognition result of the character recognition processing for the general information image from the cloud server, and acquires a target recognition result that is the recognition result of the character recognition processing for the document image in accordance with the general recognition result and the information based on the personal information image.